Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8275
    Prev
    Next
    INDEX
    Explanations

    URLs containing the user handle and code segments related to programming or technology

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1137
    +0.13
    0.5%
    1510
    +0.13
    0.4%
    866
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    896
    +0.13
    0.03
    866
    +0.13
    0.03
    1137
    +0.11
    0.04
    Negative Logits
    «<
    -0.90
     »>
    -0.89
     gaily
    -0.83
     rtn
    -0.82
     depic
    -0.77
     pymysql
    -0.77
     pcx
    -0.77
     rval
    -0.74
     plancher
    -0.74
     réservoir
    -0.73
    POSITIVE LOGITS
    ganu
    0.63
     GRATU
    0.62
    {?>
    0.62
    TAGE
    0.60
     r
    0.59
     €€
    0.58
     hect
    0.55
     elef
    0.54
    Cordial
    0.54
     d
    0.52
    Activations Density 0.182%

    No Known Activations